Re: [PATCH] KVM: x86: add hint to skip hidden rdpkru under kvm_load_host_xsave_state

[Paolo Bonzini <pbonzini@xxxxxxxxxx>]

Nice one.  The patch can be made simpler though (I think).

On 07/05/21 18:44, Jon Kohler wrote:
 @@ -122,7 +124,7 @@ static inline u32 rdpkru(void)
>   	return 0;
>   }
>
> -static inline void __write_pkru(u32 pkru)
> +static inline void __write_pkru(u32 pkru, bool skip_comparison)
>   {
>   }
>   #endif
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index cebdaa1e3cf5..cd95adbd140c 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -912,10 +912,10 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu)
>   	}
>
>   	if (static_cpu_has(X86_FEATURE_PKU) &&
> -	    (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) ||
> -	     (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU)) &&
> -	    vcpu->arch.pkru != vcpu->arch.host_pkru)
> -		__write_pkru(vcpu->arch.pkru);
> +	    vcpu->arch.pkru != vcpu->arch.host_pkru &&
> +	    ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) ||
> +	     kvm_read_cr4_bits(vcpu, X86_CR4_PKE)))
> +		__write_pkru(vcpu->arch.pkru, false);

This can be optimized as well, can't it?  This means that the only case 
that needs the rdpkru is in switch_fpu_finish, and __write_pkru can be 
removed completely:

- do the rdpkru+wrpkru in switch_fpu_finish

- just use wrpkru in KVM

Paolo


>   }
>   EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state);
>
> @@ -925,11 +925,11 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
>   		return;
>
>   	if (static_cpu_has(X86_FEATURE_PKU) &&
> -	    (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) ||
> -	     (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU))) {
> +	    ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) ||
> +	     kvm_read_cr4_bits(vcpu, X86_CR4_PKE))) {
>   		vcpu->arch.pkru = rdpkru();
>   		if (vcpu->arch.pkru != vcpu->arch.host_pkru)
> -			__write_pkru(vcpu->arch.host_pkru);
> +			__write_pkru(vcpu->arch.host_pkru, true);
>   	}
>
>   	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) {
> --
> 2.30.1 (Apple Git-130)